← Authors

Subhabrata Mukherjee

30 papers · 2012–2025 · 10 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (7) πŸ—ΊοΈ Taxonomy Completionist (58) 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (10) πŸƒ Academic Marathon (13) 🧭 Keyword Pioneer πŸ† Keyword Champion (2) 🀝 Dynamic Duo (10) πŸ—ƒοΈ Keyword Collector (100) ⚑ Prolific Year (8) πŸ’Ž Century Club (30) πŸ”₯ Unstoppable (8)

Conferences

ACL (8) EMNLP (5) NAACL (4) NIPS (4) COLING (2) ICLR (2) IJCNLP (2) AAAI (1) CVPR (1) EACL (1)

Top co-authors

Ahmed Hassan Awadallah (10) Ahmed Awadallah (5) Jianfeng Gao (4) Xiaodong Liu (4) Guoqing Zheng (3) Andrew Yates (3) Gerhard Weikum (3) Kashyap Popat (3) Debadeepta Dey (3) Xia Hu (2)

Keywords

model compression (5) knowledge distillation (5) text classification (4) neural network (4) neural architecture search (3) few-shot learning (3) mixture of expert (3) pre-trained language model (3) large language model (3) transfer learning (2) cross-lingual transfer (2) representation learning (2) semi-supervised learning (2) consistency constraint (2) stance classification (2) efficient computing (2) parameter-efficient fine-tuning (2) prompt engineering (1) natural language generation (1) natural language inference (1)

Papers

Red Queen: Exposing Latent Multi-Turn Risks in Large Language Models ACL 2025
Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing ICLR 2024
Teaching Language Models to Hallucinate Less with Synthetic Tasks ICLR 2024
Task-Based MoE for Multitask Multilingual Machine Translation EMNLP 2023
Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding EACL 2023
A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training ACL 2023
Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding ACL 2023
Small Character Models Match Large Word Models for Autocomplete Under Memory Constraints ACL 2023
AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation ACL 2023
Accelerating Dataset Distillation via Model Augmentation CVPR 2023
ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy Labels AAAI 2023
LiST: Lite Prompted Self-training Makes Parameter-efficient Few-shot Learners NAACL 2022
LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models NIPS 2022
Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models NIPS 2022
AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning EMNLP 2022
Self-Training with Weak Supervision NAACL 2021
Self-training with Few-shot Rationalization EMNLP 2021
Fairness via Representation Neutralization NIPS 2021
MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning NAACL 2021
Uncertainty-aware Self-training for Few-shot Text Classification NIPS 2020
Smart To-Do: Automatic Generation of To-Do Items from Emails ACL 2020
Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer ACL 2020
XtremeDistil: Multi-stage Distillation for Massive Multilingual Models ACL 2020
STANCY: Stance Classification Based on Consistency Cues EMNLP 2019
OpenKI: Integrating Open Information Extraction and Knowledge Bases with Relation Inference NAACL 2019
STANCY: Stance Classification Based on Consistency Cues IJCNLP 2019
DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning EMNLP 2018
Sentiment Aggregation using ConceptNet Ontology IJCNLP 2013
YouCat: Weakly Supervised Youtube Video Categorization System from Meta Data & User Comments using WordNet & Wikipedia COLING 2012
Sentiment Analysis in Twitter with Lightweight Discourse Analysis COLING 2012